Title: illumin8 Sales Pipeline
1Adding Value Through Intelligent Search
Association of American Publishers Professional
and Scholarly Publishers DivisionAnnual
Conference February 4th-6th, 2009Renaissance
Mayflower Hotel, Washington, DC
Joe BuzzangaProduct Manager, Elsevierj.buzzanga_at_
elsevier.com
2Topics
- Unlocking Content
- Standard Approaches to Information Retrieval
- Semantics and Natural Language Processing
- Conclusion
2
2
3Unlocking Content
- Our Challenge
- Corporate RD always under pressure
- Content continues to grow
- Current methods are not sufficient
- Helping our customers innovate and maximize their
ROI through superior information tools and methods
3
3
4Digital Universe 10X Growth in 5 Years
Searching for meaning in the content of
unstructured data like images, video clips,
documents, and the numbers and characters in
databases is the rocket science of the digital
universe. IDC
Source IDC Whitepaper, The Diverse and Exploding
Digital Universe, March 2008
5Information Pervades our Experience
5
5
6Standard Approaches Current Search Has Reached
Its Limit
A keyword search for food sweetener will yield
over 1,000,000 links to documents.
7Framework for Standard Approaches
Human Index
Simple Model
Search
Meta Data
Human Index
Print Collections
Surrogate Record
Search
- Traditional card catalog, periodical index
8Framework for Standard Approaches
Meta Data
Human Index
Digital Bibliographic AI
Digital Index
Surrogate Record
Search
Hybrid Index
Results
- Digital bibliographic AI
- Semi-structured records
- Content under editorial control
- Application of controlled terms
- Application of digital indexing
- Results need to be organized and ranked
- additional access points (e.g., facets, tags..)
9Framework for Standard Approaches
Web
- No Human Intervention
- Content unstructured, uncontrolled and
unmeasurable - Crawling is inherently imperfect
- Typically Keyword indexing
- Ranking of results becomes critical
10Using Natural Language Processing (NLP) in Search
- Premium Scientific
- Patent
- Web
NLP Applied
Problems, Solutions, Benefits
Semantic Index
-Crawl -Load
Search
NLP Applied
Results
Fuse, Classify, Summarize
NLP applied throughout the system index, query,
result set
11Taking Search Beyond Keyword
- Keyword Indexing
- Meaning is lost
12Concluding Unscientific Postscript
- New tools needed to handle content
- Humans dont scale computers dont think
- Perspectivism
- The value in a particular piece of content is
relative to the users interest - May be multiple dimensions of interest
- May be multiple atomic information elements
embedded in the content - And may go undetected by standard search tools
- Emerging NLP and Semantic tools represent an
evolutionary step
12
12